Predicting children's perceived reading proficiency with prosody modeling

Reading is a foundational skill and the focus of school-level education efforts across countries. The assessment of linguistic competence from oral reading has long been the subject of scientific studies linking the reader's comprehension of the text to various measures of oral reading fluency. Given the time and resource intensive nature of such assessment, it is of interest to automate the prediction of reading fluency from audio recordings using the same pedagogical rubrics. Given recent findings about the importance of prosody to the communicative purpose of reading aloud, we discuss new approaches to modeling it reliably for the automatic assessment task. We present a new data set of children's oral reading screened for minimum word decoding skill and rated for comprehensibility by two human experts. We develop a system for the automatic prediction of rater scores that also facilitates insights about the complementarity and inter-dependence of computed lexical accuracy, rate and prosodic features as corroborated by multiple performance measures. With achieved values of correlation and agreement that surpass the corresponding inter-rater measures, we also show how text-dependent prosodic features, informed by speech rate and speaking style, contribute prominently to system performance.

Automated summary

Reading is a foundational skill that is given great importance in education systems across countries. The assessment of linguistic competence through oral reading has been the focus of scientific studies, connecting the reader's comprehension to various measures of oral reading fluency. As this assessment requires significant time and resources, there is interest in automating the prediction of reading fluency using the same pedagogical rubrics. This study discusses new approaches to modeling prosody for automatic assessment, highlighting the importance of prosodic features informed by speech rate and speaking style in system performance.